Request-based DM will also make use of per_bio_data_size.
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Device mapper used the field bi_private to point to dm_target_io. However,
since kernel 3.15, the bi_private field is unused, and so the targets do
not need to save and restore this field.

This patch removes code that saves and restores bi_private from dm-cache,
dm-snapshot and dm-verity.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Remove DM's unneeded NULL tests before calling these destroy functions,
now that they check for NULL, thanks to these v4.3 commits:
3942d299 ("mm/slab_common: allow NULL cache pointer in kmem_cache_destroy()")
4e3ca3e0 ("mm/mempool: allow NULL `pool' pointer in mempool_destroy()")

The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@ expression x; @@
-if (x != NULL)
  \(kmem_cache_destroy\|mempool_destroy\|dma_pool_destroy\)(x);
// </smpl>
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Both free_io_migration() and issue_discard() dereference a migration
that was just freed.  Fix those by saving off the migrations's cache
object before freeing the migration.  Also cleanup needless mg->cache
dereferences now that the cache object is available directly.

Fixes: e44b6a5a ("dm cache: move wake_waker() from free_migrations() to where it is needed")
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Eliminate __cell_release() since it only had one caller that always
released the cell holder.

Switch cell_error_with_code() to using free_prison_cell() for the sake
of consistency.
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

There were two cases where dm_cell_visit_release() was being called,
which removes the cell from the prison's rbtree, but the callers didn't
also return the cell to the mempool.  Fix this by having them call
free_prison_cell().

This leak manifested as the 'kmalloc-96' slab growing until OOM.

Fixes: 651f5fa2 ("dm cache: defer whole cells")
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 4.1+

As generic_make_request() is now able to handle arbitrarily sized bios,
it's no longer necessary for each individual block driver to define its
own ->merge_bvec_fn() callback. Remove every invocation completely.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: drbd-user@lists.linbit.com
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: Sage Weil <sage@inktank.com>
Cc: Alex Elder <elder@kernel.org>
Cc: ceph-devel@vger.kernel.org
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Neil Brown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Acked-by: NeilBrown <neilb@suse.de> (for the 'md' bits)
Acked-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NKent Overstreet <kent.overstreet@gmail.com>
[dpark: also remove ->merge_bvec_fn() in dm-thin as well as
 dm-era-target, and resolve merge conflicts]
Signed-off-by: NDongsu Park <dpark@posteo.net>
Signed-off-by: NMing Lin <ming.l@ssi.samsung.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

This stops spurious wake ups from calls to prealloc_free_structs().
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Commit 665022d7 ("dm cache: avoid calls to prealloc_free_structs() if
possible") introduced a regression that caused the removal of a DM cache
device to hang in cache_postsuspend()'s call to wait_for_migrations()
with the following stack trace:

  [<ffffffff81651457>] schedule+0x37/0x80
  [<ffffffffa041e21b>] cache_postsuspend+0xbb/0x470 [dm_cache]
  [<ffffffff810ba970>] ? prepare_to_wait_event+0xf0/0xf0
  [<ffffffffa0006f77>] dm_table_postsuspend_targets+0x47/0x60 [dm_mod]
  [<ffffffffa0001eb5>] __dm_destroy+0x215/0x250 [dm_mod]
  [<ffffffffa0004113>] dm_destroy+0x13/0x20 [dm_mod]
  [<ffffffffa00098cd>] dev_remove+0x10d/0x170 [dm_mod]
  [<ffffffffa00097c0>] ? dev_suspend+0x240/0x240 [dm_mod]
  [<ffffffffa0009f85>] ctl_ioctl+0x255/0x4d0 [dm_mod]
  [<ffffffff8127ac00>] ? SYSC_semtimedop+0x280/0xe10
  [<ffffffffa000a213>] dm_ctl_ioctl+0x13/0x20 [dm_mod]
  [<ffffffff811fd432>] do_vfs_ioctl+0x2d2/0x4b0
  [<ffffffff81117d5f>] ? __audit_syscall_entry+0xaf/0x100
  [<ffffffff81022636>] ? do_audit_syscall_entry+0x66/0x70
  [<ffffffff811fd689>] SyS_ioctl+0x79/0x90
  [<ffffffff81023e58>] ? syscall_trace_leave+0xb8/0x110
  [<ffffffff81654f6e>] entry_SYSCALL_64_fastpath+0x12/0x71

Fix this by accounting for the call to prealloc_data_structs()
immediately _before_ the call as opposed to after.  This is needed
because it is possible to break out of the control loop after the call
to prealloc_data_structs() but before prealloc_used was set to true.
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

This reverts commit 386cb7cd.

Taking the wake_worker() out of free_migration() will slow writeback
dramatically, and hence adaptability.

Say we have 10k blocks that need writing back, but are only able to
issue 5 concurrently due to the migration bandwidth: it's imperative
that we wake_worker() immediately after migration completion; waiting
for the next 1 second wake up (via do_waker) means it'll take a long
time to write that all back.
Reported-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Currently we have two different ways to signal an I/O error on a BIO:

 (1) by clearing the BIO_UPTODATE flag
 (2) by returning a Linux errno value to the bi_end_io callback

The first one has the drawback of only communicating a single possible
error (-EIO), and the second one has the drawback of not beeing persistent
when bios are queued up, and are not passed along from child to parent
bio in the ever more popular chaining scenario.  Having both mechanisms
available has the additional drawback of utterly confusing driver authors
and introducing bugs where various I/O submitters only deal with one of
them, and the others have to add boilerplate code to deal with both kinds
of error returns.

So add a new bi_error field to store an errno value directly in struct
bio and remove the existing mechanisms to clean all this up.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

If no work was performed then prealloc_data_structs() wasn't ever called
so there isn't any need to call prealloc_free_structs().
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Refactor writeback_some_dirty_blocks() to avoid prealloc_data_structs()
if the policy doesn't have any dirty blocks ready for writeback.
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

All methods that queue work call wake_worker() as you'd expect.
E.g. cell_defer, defer_bio, quiesce_migration (which is called by
writeback, promote, demote_then_promote, invalidate, discard, etc).
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

There is currently no way to see that the needs_check flag has been set
in the metadata.  Display 'needs_check' in the cache status if it is set
in the cache metadata.

Also, update cache documentation.
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

The policy tick() method is normally called from interrupt context.
Both the mq and smq policies do some bottom half work for the tick
method in their map functions.  However if no IO is going through the
cache, then that bottom half work doesn't occur.  With these policies
this means recently hit entries do not age and do not get written
back as early as we'd like.

Fix this by introducing a new 'can_block' parameter to the tick()
method.  When this is set the bottom half work occurs immediately.
'can_block' is set when the tick method is called every second by the
core target (not in interrupt context).
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Having the DM device name associated with the ERR or INFO message is
very helpful.
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

If a cache metadata operation fails (e.g. transaction commit) the
cache's metadata device will abort the current transaction, set a new
needs_check flag, and the cache will transition to "read-only" mode.  If
aborting the transaction or setting the needs_check flag fails the cache
will transition to "fail-io" mode.

Once needs_check is set the cache device will not be allowed to
activate.  Activation requires write access to metadata.  Future work is
needed to add proper support for running the cache in read-only mode.

Once in fail-io mode the cache will report a status of "Fail".

Also, add commit() wrapper that will disallow commits if in read_only or
fail mode.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

When the cache is idle, writeback work was only being issued every
second.  With this change outstanding writebacks are streamed
constantly.  This offers a writeback performance improvement.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

When considering whether to move a block to the cache we already give
preferential treatment to discarded blocks, since they are cheap to
promote (no read of the origin required since the data is junk).

The same is true of blocks that are about to be completely
overwritten, so we likewise boost their promotion chances.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Currently individual bios are deferred to the worker thread if they
cannot be processed immediately (eg, a block is in the process of
being moved to the fast device).

This patch passes whole cells across to the worker.  This saves
reaquiring the cell, and also collects bios destined for the same block
together, which allows them to be mapped with a single look up to the
policy.  This reduces the overhead of using dm-cache.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

We only allow non critical writeback if the origin is idle.  It is up
to the policy to decide what writeback work is critical.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

A little class that keeps track of the volume of io that is in flight,
and the length of time that a device has been idle for.

FIXME: rather than jiffes, may be best to use ktime_t (to support faster
devices).
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

There is a race between a policy deciding to replace a cache entry,
the core target writing back any dirty data from this block, and other
IO threads doing IO to the same block.

This sort of problem is avoided most of the time by the core target
grabbing a bio prison cell before making the request to the policy.
But for a demotion the core target doesn't know which block will be
demoted, so can't do this in advance.

Fix this demotion race by introducing a callback to the policy interface
that allows the policy to grab the cell on behalf of the core target.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org

Commit c4cf5261 ("bio: skip atomic inc/dec of ->bi_remaining for
non-chains") regressed all existing callers that followed this pattern:
 1) saving a bio's original bi_end_io
 2) wiring up an intermediate bi_end_io
 3) restoring the original bi_end_io from intermediate bi_end_io
 4) calling bio_endio() to execute the restored original bi_end_io

The regression was due to BIO_CHAIN only ever getting set if
bio_inc_remaining() is called.  For the above pattern it isn't set until
step 3 above (step 2 would've needed to establish BIO_CHAIN).  As such
the first bio_endio(), in step 2 above, never decremented __bi_remaining
before calling the intermediate bi_end_io -- leaving __bi_remaining with
the value 1 instead of 0.  When bio_inc_remaining() occurred during step
3 it brought it to a value of 2.  When the second bio_endio() was
called, in step 4 above, it should've called the original bi_end_io but
it didn't because there was an extra reference that wasn't dropped (due
to atomic operations being optimized away since BIO_CHAIN wasn't set
upfront).

Fix this issue by removing the __bi_remaining management complexity for
all callers that use the above pattern -- bio_chain() is the only
interface that _needs_ to be concerned with __bi_remaining.  For the
above pattern callers just expect the bi_end_io they set to get called!
Remove bio_endio_nodec() and also remove all bio_inc_remaining() calls
that aren't associated with the bio_chain() interface.

Also, the bio_inc_remaining() interface has been moved local to bio.c.

Fixes: c4cf5261 ("bio: skip atomic inc/dec of ->bi_remaining for non-chains")
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Struct bio has an atomic ref count for chained bio's, and we use this
to know when to end IO on the bio. However, most bio's are not chained,
so we don't need to always introduce this atomic operation as part of
ending IO.

Add a helper to elevate the bi_remaining count, and flag the bio as
now actually needing the decrement at end_io time. Rename the field
to __bi_remaining to catch any current users of this doing the
incrementing manually.

For high IOPS workloads, this reduces the overhead of bio_endio()
substantially.
Tested-by: NRobert Elliott <elliott@hp.com>
Acked-by: NKent Overstreet <kent.overstreet@gmail.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NJens Axboe <axboe@fb.com>

To be future-proof and for better readability the time comparisons are modified
to use time_in_range() and time_after() instead of plain, error-prone math.
Signed-off-by: NManuel Schölling <manuel.schoelling@gmx.de>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Introduce a new variable to count the number of allocated migration
structures.  The existing variable cache->nr_migrations became
overloaded.  It was used to:

 i) track of the number of migrations in flight for the purposes of
    quiescing during suspend.

 ii) to estimate the amount of background IO occuring.

Recent discard changes meant that REQ_DISCARD bios are processed with
a migration.  Discards are not background IO so nr_migrations was not
incremented.  However this could cause quiescing to complete early.

(i) is now handled with a new variable cache->nr_allocated_migrations.
cache->nr_migrations has been renamed cache->nr_io_migrations.
cleanup_migration() is now called free_io_migration(), since it
decrements that variable.

Also, remove the unused cache->next_migration variable that got replaced
with with prealloc_structs a while ago.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org

We never bother caching a partial block that is at the back end of the
origin device.  No cell ever gets locked, but the calling code was
assuming it was and trying to release it.

Now the code only releases if the cell has been set to a non NULL
value.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org

If the incoming bio is a WRITE and completely covers a block then we
don't bother to do any copying for a promotion operation.  Once this is
done the cache block and origin block will be different, so we need to
set it to 'dirty'.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org

Overwrite causes the cache block and origin blocks to diverge, which
is only allowed in writeback mode.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org

Otherwise the cache blocks may span two discard blocks, which we don't
handle when doing the discard lookup.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

It is more correct to hold the cell before checking the discard state.
These flags are only used as hints to the policy so this change will
have negligable effect.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

The discard block size can change if the origin changes size or if an
old DM cache is upgraded from using a discard block size that was equal
to cache block size.

To fix this an extent of discarded blocks is established for the purpose
of translating the old discard block size to the new in-core discard
block size and set bits.  The old (potentially huge) discard bitset is
left ondisk until it is re-written using the new in-core information on
the next successful DM cache shutdown.

Fixes: 7ae34e77 ("dm cache: improve discard support")
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Commit 7ae34e77 ("dm cache: improve discard support") needed to also:
- discontinue having DM core split the discard bios on cache block
  boundaries
- calculate the cache's discard_nr_blocks relative to the determined
  discard_block_size rather than using oblock_to_dblock()
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Loading and saving millions of block mappings takes time.  We may as
well explain what's going on, and encourage people to use a larger
cache block size.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Safely allow the discard blocksize to be larger than the cache blocksize
by using the bio prison's range locking support.  This also improves
discard performance considerly because larger discards are issued to the
dm-cache device.  The discard blocksize was always intended to be
greater than the cache blocksize.  But until now it wasn't implemented
safely.

Also, by safely restoring the ability to have discard blocksize larger
than cache blocksize we're able to significantly reduce the memory used
for the cache's discard bitset.  Before, with a small discard blocksize,
the discard bitset could get quite large because its size is a function
of the discard blocksize and the origin device's size.  For example,
previously, using a 32KB cache blocksize with a 40TB origin resulted in
1280MB of incore memory use for the discard bitset!  Now, the discard
blocksize is scaled up accordingly to ensure the discard bitset is
capped at 2**14 bits, or 16KB.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

This reverts commit d132cc6d because we
actually do want to allow the discard blocksize to be larger than the
cache blocksize.  Further dm-cache discard changes will make this
possible.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>